ARTICLE AD BOX
New Delhi: OpenAI has recently released an major upgrade to its Codex, by extending its role beyond the coding into an more active assistant across the entire software development cycle. This upgrade unveils features such as computer control, memory, automation, and deeper integrations with the developers’ tools to help users handle tasks from start to finish.
It also brings over 90 latest plugins that will combine skills, application integrations, and MCP servers, by enabling Codex to gather context and take actions across a wider range of tools.
Codex is now no longer limited to writing code. It can now also operate a user’s computer by seeing, clicking, and typing by using its own cursor. With multiple agents, tasks can run in parallel without interrupting ongoing work, which can be useful for testing an application or making frontend changes in tools that don’t offer APIs.
This application also includes an in-app browser, enabling users to interact directly with the web pages and give instructions. This feature is now useful for frontend and game development, and it is also expected to extend further over time.
Codex now also supports image generation by using a built-in model, making it easier to create visuals, mockups, and design elements within the same workflow. Codex also uses GPT-image-1.5 to generate, and it will refine images along with the code and screenshots.
In addition, more than 90 latest plugins have been unveiled, allowing the integration with tools such as JIRA, GitLab, Microsoft applications, and other developer platforms.
It also adds features such as reviewing pull requests, managing multiple terminal tabs, connecting to a remote system through SSH, and previewing files such as PDFs and spreadsheets. It also provides the summary panel that will help to track ongoing tasks, sources, and outputs in one place.
Codex now also supports automation for long-term tasks by enabling it to reuse past conversations, schedule work, and continue tasks over time. This automation can retain previously built context from existing threads by helping the workflows to stay consistent.
It can also schedule tasks in advance and automatically resume ongoing work, even across days or weeks. Codex also unveils a preview of memory by enabling it to retain useful context, such as preferences, corrections, and past inputs, to improve future tasks.
It can also suggest next steps by using context from projects, plugins, and previous activity, by helping the users to pick up where they left off with a prioritized list of actions.
English (US) ·